Scientist II/Senior Scientist I, Computational Toxicology

AbbVie•North Chicago, IL

About The Position

The Computational Toxicology group is advancing the use of data science, machine learning, and AI to improve the prediction and mechanistic understanding of drug safety across small molecules, biologics, and emerging therapeutic modalities. This role is intentionally positioned at the intersection of laboratory science and computation. We are seeking a hybrid scientist who is equally comfortable generating high-quality in vitro toxicology data at the bench and building the computational tools needed to interpret it. This individual will design and execute in vitro assays to generate mechanistic and predictive safety data, while also developing analytical pipelines, predictive models, and decision-support tools that extract maximum scientific value from that data — and from broader toxicology, pathology, and translational datasets. The successful candidate will understand firsthand how in vitro biological data are generated — including assay design, cell culture systems, experimental variability, and mechanistic interpretation — and will apply that hands-on knowledge to build computational approaches that are scientifically grounded and fit for purpose. This individual will serve as a scientific bridge across disciplines, partnering closely with toxicologists, pathologists, pharmacologists, clinicians, and data scientists to transform complex scientific questions into experimental data and actionable computational insights. Success in this role requires dual fluency in laboratory science and computational methods, scientific leadership, cross-functional influence, and the ability to drive projects from experimental design through data analysis, modeling, and implementation.

Requirements

Hands-on laboratory experience designing, executing, and troubleshooting in vitro toxicology or cell-based assays (e.g., cell culture, high-content imaging, ELISA/immunoassays, flow cytometry, or similar techniques).
Strong scientific foundation in toxicology, pharmacology, cell biology, or a related discipline, with demonstrated ability to critically evaluate experimental data and biological mechanisms.
Ability to understand scientific objectives, identify key data and knowledge gaps, and translate problems into effective experimental and computational strategies.
Working proficiency in Python and/or R with the ability to develop reproducible analytical workflows and scientific software solutions.
Experience applying statistical, machine learning, and data analysis methods to biological, translational, or safety-related datasets — including data generated from the candidate's own experiments.
Demonstrated ability to independently scope projects, prioritize competing needs, and execute complex initiatives spanning both wet-lab and computational domains.
Strong understanding of the strengths, limitations, and appropriate application of computational approaches, including classical statistics, machine learning, and AI.
Proven ability to communicate effectively with scientists from diverse disciplines, including both experimentalists and computational specialists.
Experience leading or influencing cross-functional collaborations to deliver scientific outcomes.

Nice To Haves

Experience with New Approach Methodologies (NAMs), including 3D models, organoids, organ-on-chip, or high-throughput/high-content in vitro screening platforms.
Experience working with toxicology, pathology, safety pharmacology, or clinical safety datasets.
Experience integrating multimodal datasets spanning molecular, cellular, tissue, animal, and clinical domains.
Familiarity with cloud computing, scalable data processing, and large biological data platforms.
Experience with modern AI methodologies, including large language models and generative AI applications in scientific research.
Experience developing visualization tools, dashboards, or user-facing applications for scientific audiences.

Responsibilities

Design, execute, and optimize in vitro toxicology assays (e.g., cell viability, high-content imaging, organ-on-chip, 3D/organoid, mitochondrial toxicity, genotoxicity, or immune cell-based assays) to support hazard identification and mechanistic investigation.
Generate high-quality, reproducible experimental data to characterize compound-, biologic-, or modality-specific safety liabilities.
Apply sound experimental design principles (controls, replicates, dose-response, assay validation) to ensure data are fit for downstream computational modeling.
Troubleshoot assay performance, evaluate new in vitro model systems and technologies, and stay current with advances in alternative and New Approach Methodologies (NAMs).
Collaborate with in vivo toxicologists and pathologists to contextualize in vitro findings against whole-animal and clinical safety signals.
Partner with research scientists and safety experts to define critical scientific questions and identify where in vitro experimentation and/or computational approaches can accelerate decision-making.
Translate complex biological and toxicological challenges into integrated experimental-and-analytical strategies that are scientifically grounded, practical, and scalable.
Evaluate alternative in vitro models and computational methods, selecting approaches that best align with biological context, available data, and business objectives.
Serve as a trusted scientific advisor on assay design, data interpretation, and appropriate use of machine learning and AI technologies.
Design, develop, and deploy predictive models, analytical workflows, and decision-support tools that leverage in vitro-generated data alongside toxicology, pathology, pharmacology, genomics, chemistry, and clinical datasets.
Build reproducible computational pipelines and user-friendly applications that enable scientists without programming expertise to leverage advanced analytical methods.
Collaborate with computational and data engineering teams to ensure solutions are scalable, maintainable, and fit for long-term use.
Act as a scientific translator between bench scientists, toxicologists, pathologists, clinicians, and computational teams.
Build strong partnerships across Development Sciences to understand workflows, pain points, and decision-making processes.
Lead multidisciplinary initiatives from experimental concept through data generation, modeling, and implementation.
Drive alignment among stakeholders with diverse technical and experimental backgrounds.
Clearly communicate experimental methods, computational approaches, findings, limitations, and recommendations to both technical and non-technical audiences.
Present integrated experimental and computational insights in a way that facilitates decision-making and advances program strategy.
Foster adoption of both new in vitro methodologies and computational approaches by demonstrating scientific value and practical impact.